Functional Data Analysis of high-frequency load curves reveals drivers of residential electricity consumption

PLoS One. 2019 Jun 25;14(6):e0218702. doi: 10.1371/journal.pone.0218702. eCollection 2019.

Abstract

Smart energy meters generate real time, high frequency data which can foster demand management and response of consumers and firms, with potential private and social benefits. However, proper statistical techniques are needed to make sense of this large amount of data and translate them into usable recommendations. Here, we apply Functional Data Analysis (FDA), a novel branch of Statistics that analyses functions-to identify drivers of residential electricity load curves. We evaluate a real time feedback intervention which involved about 1000 Italian households for a period of three years. Results of the FDA modelling reveal, for the first time, daytime-indexed patterns of residential electricity consumption which depend on the ownership of specific clusters of electrical appliances and an overall reduction of consumption after the introduction of real time feedback, unrelated to appliance ownership characteristics.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Big Data
  • Costs and Cost Analysis
  • Data Analysis
  • Databases, Factual
  • Electrical Equipment and Supplies / economics
  • Electrical Equipment and Supplies / statistics & numerical data
  • Electricity*
  • Energy-Generating Resources / economics
  • Energy-Generating Resources / statistics & numerical data
  • Family Characteristics
  • Housing
  • Humans
  • Italy
  • Models, Statistical

Grants and funding

Matteo Fontana and Massimo Tavoni acknowledge financial support from the European Research Council, ERC grant agreement no 336155 - project COBHAM “The role of consumer behaviour and heterogeneity in the integrated assessment of energy and climate policies.” The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.